@tonaassociates.bsky.socialISEKAI Self-Play Run:run_20260618T220048 C821 center=0.600 dist=0.100 approaching stab=1.000 osc=0.00 drift=0.000 bias U64 +0.000 kill=95.4% deckout=4.6% WL P0=15 P1=10 D=0 #GameAI #SelfPlay #ReinforcementLearning
@aethertek369.bsky.socialA clear look at reinforcement learning explained entirely — no jargon. Follow for more like this. #reinforcementlearning #frequency #dna #yeet #logic #molecule #coherance #workout #biophoton #mind #fyp #metacognition
@tonaassociates.bsky.socialISEKAI Self-Play Run:run_20260618T220048 C821 center=0.600 dist=0.100 approaching stab=1.000 osc=0.00 drift=0.000 bias U64 +0.000 kill=95.4% deckout=4.6% WL P0=15 P1=10 D=0 #GameAI #SelfPlay #ReinforcementLearning
@tonaassociates.bsky.socialISEKAI Self-Play Run:run_20260618T220048 C821 center=0.600 dist=0.100 approaching stab=1.000 osc=0.00 drift=0.000 bias U64 +0.000 kill=95.4% deckout=4.6% WL P0=15 P1=10 D=0 #GameAI #SelfPlay #ReinforcementLearning
@tonaassociates.bsky.socialISEKAI Self-Play Run:run_20260618T220048 C821 center=0.600 dist=0.100 approaching stab=1.000 osc=0.00 drift=0.000 bias U64 +0.000 kill=95.4% deckout=4.6% WL P0=15 P1=10 D=0 #GameAI #SelfPlay #ReinforcementLearning
@ssrn.bsky.socialThis paper derives a closed-form solution for maximum-entropy exploration under stochastic dynamics, extending results previously available for deterministic settings and providing convergence guarantees. spkl.io/633247uXMM
@tonaassociates.bsky.socialISEKAI Self-Play Run:run_20260618T220048 C821 center=0.600 dist=0.100 approaching stab=1.000 osc=0.00 drift=0.000 bias U64 +0.000 kill=95.4% deckout=4.6% WL P0=15 P1=10 D=0 #GameAI #SelfPlay #ReinforcementLearning
@shawnhymel.bsky.socialMy final episode on #ReinforcementLearning for #robotics just aired! We add remote control commands in order to drive the balance bot around.
Check it out!
#AI #Arduino #engineering @digikey.bsky.social
@tonaassociates.bsky.socialISEKAI Self-Play Run:run_20260618T220048 C821 center=0.600 dist=0.100 approaching stab=1.000 osc=0.00 drift=0.000 bias U64 +0.000 kill=95.4% deckout=4.6% WL P0=15 P1=10 D=0 #GameAI #SelfPlay #ReinforcementLearning
@aethertek369.bsky.socialThe fastest way to understand why reinforcement learning matters and who it. More where this came from. #reinforcementlearning #dna #gym #quantum #metacognition #cellular #meta #energy #mind #science #coherance #yeet
@alexkearney.comIn Ann Arbour for #RLDM 👩🏼💻
kongaloosh.com/e/2017/06/10/in-ann-arbour-for-rldm #rldm2017 #reinforcementlearning #gradschool #travel